The Effects of Mild Over-parameterization on the Optimization Landscape of Shallow ReLU Neural Networks

Abstract

We study the effects of mild over-parameterization on the optimization landscape of a simple ReLU neural network of the form $\mathbf{x}\mapsto {\sum }_{i=1}^k\max \{0,{\mathbf{w}}_i^{\top }\mathbf{x}\}$, in a well-studied teacher-student setting where the target values are generated by the same architecture, and when directly optimizing over the population squared loss with respect to Gaussian inputs. We prove that while the objective is strongly convex around the global minima when the teacher and student networks possess the same number of neurons, it is not even \emph{locally convex} after any amount of over-parameterization. Moreover, related desirable properties (e.g., one-point strong convexity and the Polyak-Łojasiewicz condition) also do not hold even locally. On the other hand, we establish that the objective remains one-point strongly convex in \emph{most} directions (suitably defined), and show an optimization guarantee under this property. For the non-global minima, we prove that adding even just a single neuron will turn a non-global minimum into a saddle point. This holds under some technical conditions which we validate empirically. These results provide a possible explanation for why recovering a global minimum becomes significantly easier when we over-parameterize, even if the amount of over-parameterization is very moderate.

References in corpus (18)

• Neural Tangent Kernel: Convergence and Generalization in Neural Networks
• Gradient Descent Provably Optimizes Over-parameterized Neural Networks
• Convergence Analysis of Two-layer Neural Networks with ReLU Activation
• Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers
• No bad local minima: Data independent training error guarantees for multilayer neural networks
• Recovery Guarantees for One-hidden-layer Neural Networks
• Learning ReLUs via Gradient Descent
• An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis
• Generalization Error Bounds of Gradient Descent for Learning Over-parameterized Deep ReLU Networks
• On the Power and Limitations of Random Features for Understanding Neural Networks
• Can SGD Learn Recurrent Neural Networks with Provable Generalization?
• Learning Parities with Neural Networks
• Learning a Single Neuron with Gradient Methods
• The Multilinear Structure of ReLU Networks
• Approximate is Good Enough: Probabilistic Variants of Dimensional and Margin Complexity
• Learning Over-Parametrized Two-Layer ReLU Neural Networks beyond NTK
• On the Principle of Least Symmetry Breaking in Shallow ReLU Models
• Analytic Characterization of the Hessian in Shallow ReLU Models: A Tale of Symmetry

Cited by in corpus (1)

• Quickly Finding a Benign Region via Heavy Ball Momentum in Non-Convex Optimization